English

Secure and Efficient Federated Learning Through Layering and Sharding Blockchain

Cryptography and Security 2024-02-01 v5 Artificial Intelligence Information Theory math.IT

Abstract

Introducing blockchain into Federated Learning (FL) to build a trusted edge computing environment for transmission and learning has attracted widespread attention as a new decentralized learning pattern. However, traditional consensus mechanisms and architectures of blockchain systems face significant challenges in handling large-scale FL tasks, especially on Internet of Things (IoT) devices, due to their substantial resource consumption, limited transaction throughput, and complex communication requirements. To address these challenges, this paper proposes ChainFL, a novel two-layer blockchain-driven FL system. It splits the IoT network into multiple shards within the subchain layer, effectively reducing the scale of information exchange, and employs a Direct Acyclic Graph (DAG)-based mainchain as the mainchain layer, enabling parallel and asynchronous cross-shard validation. Furthermore, the FL procedure is customized to integrate deeply with blockchain technology, and a modified DAG consensus mechanism is designed to mitigate distortion caused by abnormal models. To provide a proof-of-concept implementation and evaluation, multiple subchains based on Hyperledger Fabric and a self-developed DAG-based mainchain are deployed. Extensive experiments demonstrate that ChainFL significantly surpasses conventional FL systems, showing up to a 14% improvement in training efficiency and a threefold increase in robustness.

Keywords

Cite

@article{arxiv.2104.13130,
  title  = {Secure and Efficient Federated Learning Through Layering and Sharding Blockchain},
  author = {Shuo Yuan and Bin Cao and Yao Sun and Zhiguo Wan and Mugen Peng},
  journal= {arXiv preprint arXiv:2104.13130},
  year   = {2024}
}

Comments

Accepted by IEEE Transactions on Network Science and Engineering

R2 v1 2026-06-24T01:33:33.107Z